Files
s3/weed/command/worker.go
zooqueen dd74d3e6d6 Replace AGPL MinIO fork with Apache-2.0 SeaweedFS fork; rebrand CLI weed->s3
hanzoai/s3 was an AGPL-3.0 MinIO fork whose network-copyleft blocks embedding
and reselling as a managed service. Replace it wholesale with a fork of
SeaweedFS (github.com/seaweedfs/seaweedfs, Apache-2.0, Go) which ships a
built-in S3 gateway + Filer.

- License: AGPL-3.0 -> Apache-2.0 (upstream LICENSE kept verbatim, incl.
  "Copyright 2025 Chris Lu"); NOTICE added crediting SeaweedFS. No AGPL/BUSL/
  SSPL/GPL or enterprise ("ee") files remain.
- Module: go.mod path set to github.com/hanzoai/s3 with a self-replace
  (replace github.com/seaweedfs/seaweedfs => ./) so the ~1800 internal Go files
  keep their upstream import paths with zero churn. Internal identifiers and
  import paths are intentionally NOT renamed.
- CLI rebrand: the binary is built as `s3` (was `weed`); root usage, per-command
  help/usage/flag strings, shell autocomplete program name, and the product name
  in CLI output now read "Hanzo S3" / `s3`. Users never see `weed`.
  (e.g. `s3 server`, `s3 filer`, `s3 master`, `s3 volume`, `s3 s3`, `s3 mount`.)
- Build: `make` (or `go build -o s3 ./weed`) builds the `s3` binary green;
  `cmd/weed-db` and `cmd/weed-sql` also build; `go vet ./weed/command/` clean.
- README/LLM.md rewritten for Hanzo S3; AGENTS.md/CLAUDE.md symlinks preserved.
- Dropped a 33MB prebuilt Mach-O `stress` binary upstream had committed; `.gitignore`
  updated to ignore the `s3` build output.
2026-06-18 23:41:25 -07:00

81 lines
3.8 KiB
Go

package command
import (
"time"
"github.com/seaweedfs/seaweedfs/weed/util"
"github.com/seaweedfs/seaweedfs/weed/util/grace"
)
var cmdWorker = &Command{
UsageLine: "worker -admin=<admin_server> [-id=<worker_id>] [-jobType=all] [-workingDir=<path>] [-heartbeat=15s] [-reconnect=5s] [-maxDetect=1] [-maxExecute=4] [-metricsPort=<port>] [-metricsIp=<ip>] [-debug]",
Short: "start a plugin.proto worker process",
Long: `Start an external plugin worker using weed/pb/plugin.proto over gRPC.
This command provides plugin job type handlers for cluster maintenance,
including descriptor delivery, heartbeat/load reporting, detection, and execution.
Behavior:
- Use -jobType to choose handlers by category or explicit name (comma-separated)
- Categories: "all" (every registered handler), "default" (lightweight jobs),
"heavy" (resource-intensive jobs like erasure coding)
- Explicit job type names and aliases are still supported (e.g. "vacuum", "ec")
- Categories and explicit names can be mixed (e.g. "default,iceberg")
- Use -workingDir to persist worker.id for stable worker identity across restarts
- Use -metricsPort/-metricsIp to expose /health, /ready, and /metrics
Examples:
s3 worker -admin=localhost:23646
s3 worker -admin=localhost:23646 -jobType=all
s3 worker -admin=localhost:23646 -jobType=default
s3 worker -admin=localhost:23646 -jobType=heavy
s3 worker -admin=localhost:23646 -jobType=default,iceberg
s3 worker -admin=localhost:23646 -jobType=vacuum,volume_balance
s3 worker -admin=localhost:23646 -jobType=erasure_coding
s3 worker -admin=admin.example.com:23646 -id=plugin-vacuum-a -heartbeat=10s
s3 worker -admin=localhost:23646 -workingDir=/var/lib/seaweedfs-plugin
s3 worker -admin=localhost:23646 -metricsPort=9327 -metricsIp=0.0.0.0
`,
}
var (
workerAdminServer = cmdWorker.Flag.String("admin", "localhost:23646", "admin server address")
workerID = cmdWorker.Flag.String("id", "", "worker ID (auto-generated when empty)")
workerWorkingDir = cmdWorker.Flag.String("workingDir", "", "working directory for persistent worker state")
workerJobType = cmdWorker.Flag.String("jobType", defaultPluginWorkerJobTypes, "job types or categories to serve: all, default, heavy, or explicit names/aliases such as ec, balance, iceberg (comma-separated)")
workerHeartbeat = cmdWorker.Flag.Duration("heartbeat", 15*time.Second, "heartbeat interval")
workerReconnect = cmdWorker.Flag.Duration("reconnect", 5*time.Second, "reconnect delay")
workerMaxDetect = cmdWorker.Flag.Int("maxDetect", 1, "max concurrent detection requests")
workerMaxExecute = cmdWorker.Flag.Int("maxExecute", 4, "max concurrent execute requests")
workerAddress = cmdWorker.Flag.String("address", "", "worker address advertised to admin")
workerMetricsPort = cmdWorker.Flag.Int("metricsPort", 0, "Prometheus metrics listen port")
workerMetricsIp = cmdWorker.Flag.String("metricsIp", "0.0.0.0", "Prometheus metrics listen IP")
workerDebug = cmdWorker.Flag.Bool("debug", false, "serves runtime profiling data via pprof on the port specified by -debug.port")
workerDebugPort = cmdWorker.Flag.Int("debug.port", 6060, "http port for debugging")
)
func init() {
cmdWorker.Run = runWorker
}
func runWorker(cmd *Command, args []string) bool {
if *workerDebug {
grace.StartDebugServer(*workerDebugPort)
}
*workerWorkingDir = util.ResolvePath(*workerWorkingDir)
return runPluginWorkerWithOptions(pluginWorkerRunOptions{
AdminServer: *workerAdminServer,
WorkerID: *workerID,
WorkingDir: *workerWorkingDir,
JobTypes: *workerJobType,
Heartbeat: *workerHeartbeat,
Reconnect: *workerReconnect,
MaxDetect: *workerMaxDetect,
MaxExecute: *workerMaxExecute,
Address: *workerAddress,
MetricsPort: *workerMetricsPort,
MetricsIP: *workerMetricsIp,
})
}